文件列表:

LICENSE (11357, 2019-04-11)
data (0, 2019-04-11)
data\__init__.py (1948, 2019-04-11)
data\__init__.pyc (3563, 2019-04-11)
data\__pycache__ (0, 2019-04-11)
data\__pycache__\__init__.cpython-34.pyc (2192, 2019-04-11)
data\__pycache__\__init__.cpython-36.pyc (2782, 2019-04-11)
data\__pycache__\coco.cpython-36.pyc (7417, 2019-04-11)
data\__pycache__\config.cpython-34.pyc (1569, 2019-04-11)
data\__pycache__\config.cpython-36.pyc (2024, 2019-04-11)
data\__pycache__\voc0712.cpython-34.pyc (7096, 2019-04-11)
data\__pycache__\voc0712.cpython-36.pyc (6658, 2019-04-11)
data\__pycache__\widerface.cpython-36.pyc (8618, 2019-04-11)
data\coco.py (7233, 2019-04-11)
data\coco.pyc (9097, 2019-04-11)
data\coco_labels.txt (1083, 2019-04-11)
data\config.py (3056, 2019-04-11)
data\config.pyc (2697, 2019-04-11)
data\scripts (0, 2019-04-11)
data\scripts\COCO2014.sh (1955, 2019-04-11)
data\scripts\VOC2007.sh (974, 2019-04-11)
data\scripts\VOC2012.sh (765, 2019-04-11)
data\voc0712.py (6615, 2019-04-11)
data\voc0712.pyc (8001, 2019-04-11)
data\widerface.py (11747, 2019-04-11)
data\widerface.pyc (10329, 2019-04-11)
data\worlds-largest-selfie.jpg (471393, 2019-04-11)
demo.py (9694, 2019-04-11)
face_ssd.py (25563, 2019-04-11)
fddb_test.py (12732, 2019-04-11)
imgs (0, 2019-04-11)
imgs\DSFD_demo.PNG (1581115, 2019-04-11)
imgs\DSFD_demo1.PNG (2478939, 2019-04-11)
imgs\DSFD_demo2.PNG (2169707, 2019-04-11)
imgs\DSFD_demo3.PNG (1780772, 2019-04-11)
imgs\DSFD_fddb.PNG (404161, 2019-04-11)
imgs\DSFD_framework.PNG (247319, 2019-04-11)
imgs\DSFD_widerface.PNG (649199, 2019-04-11)
... ...

## [DSFD: Dual Shot Face Detector](https://arxiv.org/abs/1810.10220) [](LICENSE) By [Jian Li](https://lijiannuist.github.io/), [Yabiao Wang](https://github.com/ChaunceyWang), [Changan Wang](https://github.com/HiKapok), [Ying Tai](https://tyshiwo.github.io/), [Jianjun Qian](http://www.escience.cn/people/JianjunQian/index.html), [Jian Yang](https://scholar.google.com/citations?user=6CIDtZQAAAAJ&hl=zh-CN&oi=sra), Chengjie Wang, Jilin Li, Feiyue Huang. ## Introduction This paper is accepted by CVPR 2019. In this paper, we propose a novel face detection network, named DSFD, with superior performance over the state-of-the-art face detectors. You can use the code to evaluate our DSFD for face detection. For more details, please refer to our paper [DSFD: Dual Shot Face Detector](https://arxiv.org/abs/1810.10220)!

Our DSFD face detector achieves state-of-the-art performance on [WIDER FACE](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/WiderFace_Results.html) and [FDDB](http://vis-www.cs.umass.edu/fddb/results.html) benchmark. ### WIDER FACE

### FDDB

## Qualitative Results

## Requirements - Torch == 0.3.1 - Torchvision == 0.2.1 - Python == 3.6 - NVIDIA GPU == Tesla P40 - Linux CUDA CuDNN ## Getting Started ### Installation Clone the github repository. We will call the cloned directory as `$DSFD_ROOT`. ```bash git clone https://github.com/TencentYoutuResearch/FaceDetection-DSFD.git cd FaceDetection-DSFD export CUDA_VISIBLE_DEVICES=0 ``` ### Evaluation 1. Download the images of [WIDER FACE](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/) and [FDDB](https://drive.google.com/open?id=17t4WULUDgZgiSy5kpCax4aooyPaz3GQH) to `$DSFD_ROOT/data/`. 2. Download our DSFD model [[微云]](https://share.weiyun.com/567x0xQ) [[google drive]](https://drive.google.com/file/d/1WeXlNYsM6dMP3xQQELI-4gxhwKUQxc3-/view?usp=sharing) trained on WIDER FACE training set to `$DSFD_ROOT/weights/`. 3. Check out [`./demo.py`](https://github.com/TencentYoutuResearch/FaceDetection-DSFD/blob/master/demo.py) on how to detect faces using the DSFD model and how to plot detection results. ``` python demo.py [--trained_model [TRAINED_MODEL]] [--img_root [IMG_ROOT]] [--save_folder [SAVE_FOLDER]] [--visual_threshold [VISUAL_THRESHOLD]] --trained_model Path to the saved model --img_root Path of test images --save_folder Path of output detection resutls --visual_threshold Confidence thresh ``` 4. Evaluate the trained model via [`./widerface_val.py`](https://github.com/TencentYoutuResearch/FaceDetection-DSFD/blob/master/widerface_val.py) on WIDER FACE. ``` python widerface_val.py [--trained_model [TRAINED_MODEL]] [--save_folder [SAVE_FOLDER]] [--widerface_root [WIDERFACE_ROOT]] --trained_model Path to the saved model --save_folder Path of output widerface resutls --widerface_root Path of widerface dataset ``` 5. Download the [eval_tool](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/support/eval_script/eval_tools.zip) to show the WIDERFACE performance. 6. Evaluate the trained model via [`./fddb_test.py`](https://github.com/sTencentYoutuResearch/FaceDetection-DSFD/blob/master/fddb_test.py) on FDDB. ``` python widerface_test.py [--trained_model [TRAINED_MODEL]] [--split_dir [SPLIT_DIR]] [--data_dir [DATA_DIR]] [--det_dir [DET_DIR]] --trained_model Path of the saved model --split_dir Path of fddb folds --data_dir Path of fddb all images --det_dir Path to save fddb results ``` 7. Download the [evaluation](http://vis-www.cs.umass.edu/fddb/evaluation.tgz) to show the FDDB performance. ### Citation If you find DSFD useful in your research, please consider citing: ``` @inproceedings{li2018***d, title={DSFD: Dual Shot Face Detector}, author={Li, Jian and Wang, Yabiao and Wang, Changan and Tai, Ying and Qian, Jianjun and Yang, Jian and Wang, Chengjie and Li, Jilin and Huang, Feiyue}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, year={2019} } ```

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：